Computer vision for fruit harvesting robots  state of the art and challenges ahead

Kapach, Keren; Barnea, Ehud; Mairon, Rotem; Edan, Yael; Ben-Shahar, Ohad

doi:10.1504/ijcvr.2012.046419

Cited by 193 publications

(141 citation statements)

References 115 publications

Supporting

Mentioning

137

Contrasting

Unclassified

Order By: Relevance

“…Furthermore, there was an added complexity of detecting the clusters while advancing along the row. Autonomous detection rates average about 85%, in general . Previous research has proven that detection rate can be improved by incorporating more advanced detection algorithms and combining human in the loop .…”

Section: Discussion: Generalizationmentioning

confidence: 99%

Design and development of a semi‐autonomous agricultural vineyard sprayer: Human–robot interaction aspects

Adamides

Katsanos

Constantinou

et al. 2017

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

This article presents the design aspects and development processes to transform a general‐purpose mobile robotic platform into a semi‐autonomous agricultural robot sprayer focusing on user interfaces for teleoperation. The hardware and the software modules that must be installed onto the system are described, with particular emphasis on human–robot interaction. Details of the technology are given focusing on the user interface aspects. Two laboratory experiments and two studies in the field to evaluate the usability of the user interface provide evidence for the increased usability of a prototype robotic system. Specifically, the study aimed to empirically evaluate the type of target selection input device mouse and digital pen outperformed Wiimote in terms of usability. A field experiment evaluated the effect of three design factors: (a) type of screen output, (b) number of views, (c) type of robot control input device. Results showed that participants were significantly more effective but less efficient when they had multiple views, than when they had a single view. PC keyboard was also found to significantly outperform PS3 gamepad in terms of interaction efficiency and perceived usability. Heuristic evaluations of different user interfaces were also performed using research‐based HRI heuristics. Finally, a study on participants’ overall user experience found that the system was evaluated positively on the User Experience Questionnaire scales.

show abstract

Section: Discussion: Generalizationmentioning

confidence: 99%

Design and development of a semi‐autonomous agricultural vineyard sprayer: Human–robot interaction aspects

Adamides

Katsanos

Constantinou

et al. 2017

Journal of Field Robotics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Hence there has been an increase in the use of 3D sensors for depth perception [9]. The advantages of 3D include encoding the object geometry and providing different viewpoints under clutter.…”

Section: Related Workmentioning

confidence: 99%

Can you pick a broccoli? 3D-vision based detection and localisation of broccoli heads in the field

Kusumam

Krajník

Pearson

et al. 2016

2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-This paper presents a 3D vision system for robotic harvesting of broccoli using low-cost RGB-D sensors. The presented method addresses the tasks of detecting mature broccoli heads in the field and providing their 3D locations relative to the vehicle. The paper evaluates different 3D features, machine learning and temporal filtering methods for detection of broccoli heads. Our experiments show that a combination of Viewpoint Feature Histograms, Support Vector Machine classifier and a temporal filter to track the detected heads results in a system that detects broccoli heads with 95.2% precision. We also show that the temporal filtering can be used to generate a 3D map of the broccoli head positions in the field.

show abstract

“…Due to the dynamic and unstructured nature of greenhouse environment, the fruit detection part is very challenging. Several types of sensors and methods are suggested, see [5,6] for reviews. This paper proposes a new approach for yellow pepper detection from images of greenhouse environments.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Image Thresholding of Yellow Peppers for a Harvesting Robot

2018

View full text Add to dashboard Cite

Abstract:The presented work is part of the H2020 project SWEEPER with the overall goal to develop a sweet pepper harvesting robot for use in greenhouses. As part of the solution, visual servoing is used to direct the manipulator towards the fruit. This requires accurate and stable fruit detection based on video images. To segment an image into background and foreground, thresholding techniques are commonly used. The varying illumination conditions in the unstructured greenhouse environment often cause shadows and overexposure. Furthermore, the color of the fruits to be harvested varies over the season. All this makes it sub-optimal to use fixed pre-selected thresholds. In this paper we suggest an adaptive image-dependent thresholding method. A variant of reinforcement learning (RL) is used with a reward function that computes the similarity between the segmented image and the labeled image to give feedback for action selection. The RL-based approach requires less computational resources than exhaustive search, which is used as a benchmark, and results in higher performance compared to a Lipschitzian based optimization approach. The proposed method also requires fewer labeled images compared to other methods. Several exploration-exploitation strategies are compared, and the results indicate that the Decaying Epsilon-Greedy algorithm gives highest performance for this task. The highest performance with the Epsilon-Greedy algorithm ( = 0.7) reached 87% of the performance achieved by exhaustive search, with 50% fewer iterations than the benchmark. The performance increased to 91.5% using Decaying Epsilon-Greedy algorithm, with 73% less number of iterations than the benchmark.

show abstract

Computer vision for fruit harvesting robots state of the art and challenges ahead

Cited by 193 publications

References 115 publications

Design and development of a semi‐autonomous agricultural vineyard sprayer: Human–robot interaction aspects

Design and development of a semi‐autonomous agricultural vineyard sprayer: Human–robot interaction aspects

Can you pick a broccoli? 3D-vision based detection and localisation of broccoli heads in the field

Adaptive Image Thresholding of Yellow Peppers for a Harvesting Robot

Contact Info

Product

Resources

About

Computer vision for fruit harvesting robots  state of the art and challenges ahead

Cited by 193 publications

References 115 publications

Design and development of a semi‐autonomous agricultural vineyard sprayer: Human–robot interaction aspects

Design and development of a semi‐autonomous agricultural vineyard sprayer: Human–robot interaction aspects

Can you pick a broccoli? 3D-vision based detection and localisation of broccoli heads in the field

Adaptive Image Thresholding of Yellow Peppers for a Harvesting Robot

Contact Info

Product

Resources

About

Computer vision for fruit harvesting robots state of the art and challenges ahead